Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2054 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1837. Min Range: -1.1837

Max Act: 1.1837. Min Act: -0.0000

Data Index: 339607 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.1837. Min Range: -1.1837

Max Act: 1.0994. Min Act: -0.0000

Data Index: 664211 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9737. Min Act: -0.0000

Data Index: 645105 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9757. Min Act: -0.0000

Data Index: 651936 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 1.1837. Min Range: -1.1837

Max Act: 1.0074. Min Act: -0.0000

Data Index: 530901 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9736. Min Act: -0.0000

Data Index: 856367 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9838. Min Act: -0.0000

Data Index: 403798 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9058. Min Act: -0.0000

Data Index: 1537241 (Python Code)

Max Activating Token Index: 386

Text #8

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9073. Min Act: -0.0000

Data Index: 211921 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1334018 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1590935 (Python Code)

Max Activating Token Index: 747

Text #11

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1402760 (Python Code)

Max Activating Token Index: 897

Text #12

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.8847. Min Act: -0.0000

Data Index: 818612 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1417346 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1358452 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.8616. Min Act: -0.0000

Data Index: 575491 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1211199 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.8865. Min Act: -0.0000

Data Index: 837524 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1615427 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 1.1837. Min Range: -1.1837

Max Act: 0.8631. Min Act: -0.0000

Data Index: 615245 (C4 (Web Text))

Max Activating Token Index: 368